mlsanityData to 7 Oct 2026

On the Value of Target Data in Transfer Learning

arXiv 2002.04747 ↗First posted 12 Feb 2020cs.LG stat.MLcited by 62

Not on the map. Why?

Abstract (arXiv)

We aim to understand the value of additional labeled or unlabeled target data in transfer learning, for any given amount of source data; this is motivated by practical questions around minimizing sampling costs, whereby, target data is usually harder or costlier to acquire than source data, but can yield better accuracy. To this aim, we establish the first minimax-rates in terms of both source and target sample sizes, and show that performance limits are captured by new notions of discrepancy between source and target, which we refer to as transfer exponents.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 9; 2023: 12; 2024: 15; 2025: 8; 2026: 8.

62 papers.

Sort:

By area:

  1. 2023Transformers as Algorithms: Generalization and Stability in In-context Learningcited by 220
  2. 2021Transfer Learning under High-dimensional Generalized Linear Modelscited by 69
  3. 2021Model Zoo: A Growing "Brain" That Learns Continuallycited by 53
  4. 2023AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptationcited by 48
  5. 2021How Fine-Tuning Allows for Effective Meta-Learningcited by 41
  6. 2021Near-Optimal Linear Regression under Distribution Shiftcited by 40
  7. 2022Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guaranteescited by 34
  8. 2024Understanding Forgetting in Continual Learning with Linear Regressioncited by 26
  9. 2022The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shiftcited by 25
  10. 2022Transfer Learning for Contextual Multi-armed Banditscited by 24
  11. 2021Weighted Training for Cross-Task Learningcited by 22
  12. 2023Identification of Negative Transfers in Multitask Learning Using Surrogate Modelscited by 20
38 more
  1. 2023Pseudo-Labeling for Kernel Ridge Regression under Covariate Shiftcited by 17
  2. 2022Dimensionless machine learning: Imposing exact units equivariancecited by 16
  3. 2021Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithmcited by 14
  4. 2022The Value of Out-of-Distribution Datacited by 12
  5. 2022On the Generalization for Transfer Learning: An Information-Theoretic Analysiscited by 11
  6. 2023Reliable learning in challenging environmentscited by 9
  7. 2023Limits of Model Selection under Transfer Learningcited by 9
  8. 2023Model-free Test Time Adaptation for Out-Of-Distribution Detectioncited by 9
  9. 2023Best-Effort Adaptationcited by 7
  10. 2023Towards the Theory of Unsupervised Federated Learning: Non-asymptotic Analysis of Federated EM Algorithmscited by 7
  11. 2024On f-Divergence Principled Domain Adaptation: An Improved Frameworkcited by 6
  12. 2024Transfer Learning Beyond Bounded Density Ratioscited by 6
  13. 2025Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Modelscited by 6
  14. 2021Universal and data-adaptive algorithms for model selection in linear contextual banditscited by 5
  15. 2024Transfer Learning Study of Motion Transformer-based Trajectory Predictionscited by 5
  16. 2021Adaptive transfer learningcited by 4
  17. 2024Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalizationcited by 4
  18. 2025Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guaranteescited by 4
  19. 2025CoT Information: Improved Sample Complexity under Chain-of-Thought Supervisioncited by 4
  20. 2022Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classificationcited by 3
  21. 2023Classification Tree Pruning Under Covariate Shiftcited by 3
  22. 2023Tight Rates in Supervised Outlier Transfer Learningcited by 3
  23. 2024Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participationcited by 3
  24. 2024Transfer Learning for Latent Variable Network Modelscited by 3
  25. 2024Distributionally robust risk evaluation with an isotonic constraintcited by 3
  26. 2024Help Me Help You: The Aggregate Value of Source and Target Data in Transfer Learningcited by 3
  27. 2022Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localizationcited by 2
  28. 2024Trans-Glasso: A Transfer Learning Approach to Precision Matrix Estimationcited by 2
  29. 2025On The Statistical Complexity of Offline Decision-Makingcited by 2
  30. 2025Neyman-Pearson Classification under Both Null and Alternative Distributions Shiftcited by 2
  31. 2021Direct domain adaptation through reciprocal linear transformationscited by 1
  32. 2024Learning Tree-Structured Composition of Data Augmentationcited by 1
  33. 2024Understanding Transfer Learning via Mean-field Analysiscited by 1
  34. 2025On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspectivecited by 1
  35. 2026When More Data Doesn't Help: Limits of Adaptation in Multitask Learningcited by 1
  36. 2026Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Biascited by 1
  37. 2021Learning to Transfer: A Foliated Theorycited by 0
  38. 2022Transfer-Learning Across Datasets with Different Input Dimensions: An Algorithm and Analysis for the Linear Regression Casecited by 0

50 most cited of 62 All 62 (JSON)